Music and Speech Modelling
QMUL ECS 729 Spring 2017
QMUL ECS 729 Spring 2017
Jonathan Mark Pigrem
This project investigates expressive timing in popular music and the potential influence of recording technology and common studio practice. Since the birth of recording in 1875, the technology used to record and document performances has influenced both the sound of recoded music and the very nature of recorded performances. Just how much influences does midi sequencing and audio looping have on the expressive qualities of popular music?
Through tempo analysis of 13 UK No.1 singles (one every 5 years since the birth of the singles chart in 1952) the project demonstrates the chronological effects of recording technology on expressive timing in popular music.
Kieran Alan Labram
Queens of the Stone Age have had five different drummers over their 20 years as a band. A common subject for debate amongst fans is what drummer was the best, whether drummers who sped up the tempo when performing live are more preferable to ones who played more closely to the original recording.
Robert Jan Blaauboer
Looking at Hip-Hop tracks where syllables and stressed syllables have been annotated. An analysis is performed to detect rhythmic motifs for multiple vocal tracks of the same performer.
Petr Choulik
When listening to music, people often refer to features such as the ‘groove’ or the drummer being ‘ahead’ or ‘behind’ the beat. The aim of this project is to evaluate the relationship between the features embedded in the music and the perception of the pulse. For example, if we say that a drummer is playing ‘ahead’ of the beat, do we perceive the beat to be delayed compared to the onsets of the drums?
Samuel Perry
The project aimed to improve the performance of a prototype project developed for offline concatenative synthesis in python. Focus was placed on improving the aesthetics of output through the modification of the programs methods for analysing audio and synthesizing output. Output was then evaluated qualitatively to determine the overall improvement of performance, and to compare with similar systems.
Henry Albert Finn
Explores how the acoustic properties of the voice change when the speaker speaks at different dynamic levels, and attempts to emulate these changes through modification of speech samples.